RL-Exec: Impact-Aware Reinforcement Learning for Opportunistic Optimal Liquidation, Outperforms TWAP and a Book-Liquidity VWAP on BTC-USD Replays

By Enzo Duflot, Stanislas Robineau

Published 2025-10-30

Everscope rating

1782.7

Relevance to quantitative trading

9 / 10

Implementation complexity

6 / 10

Reproducibility

5 / 5

About this paper

Methodology: RL-Exec (Impact-Aware PPO for Opportunistic Liquidation). Problem types: Reinforcement Learning, Algorithmic Execution, Optimization.

arXiv:2511.07434 · Code · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.